Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a79520da52f822c46dba3c748e8dd081eb749eeec830a360509447dc2e67f12
+oid sha256:29470ec27598bc3d372335ec5aa6610a147aa417ceacd8b5c5292a7a091000df
 size 332316480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac12a86c430b6a58b90d0cb3ab8eaf564b299708841d892247a5a4912241877
+oid sha256:8b6d958c100711c0442db6eff65805efdb0fd00ddf3eef7ec7892ca958d7f879
 size 169157892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362229003ce58a811c7ba2395bcef67f039955abfab5ad54bb81ce19b96652e5
+oid sha256:de750bf2d834557cda66e5c74e8bb7c1e12b90cc43596f1a40e7a0095d2e9154
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022892025944296072,
+  "epoch": 0.02518122853872568,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 20.602,
       "eval_steps_per_second": 2.576,
       "step": 90
+    },
+    {
+      "epoch": 0.023655093475772607,
+      "grad_norm": 1.0483613014221191,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.5108,
+      "step": 93
+    },
+    {
+      "epoch": 0.024418161007249143,
+      "grad_norm": 1.0317051410675049,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.4549,
+      "step": 96
+    },
+    {
+      "epoch": 0.02518122853872568,
+      "grad_norm": 0.9832442998886108,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.4761,
+      "step": 99
+    },
+    {
+      "epoch": 0.02518122853872568,
+      "eval_loss": 1.5044512748718262,
+      "eval_runtime": 321.63,
+      "eval_samples_per_second": 20.589,
+      "eval_steps_per_second": 2.574,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.729312234602496e+16,
+  "total_flos": 4.102243458062746e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null